VictoriaMetrics/lib/promscrape/discovery/dns/dns.go
Aliaksandr Valialkin d5a599badc
lib/promauth: follow-up for e16d3f5639
- Make sure that invalid/missing TLS CA file or TLS client certificate files at vmagent startup
  don't prevent from processing the corresponding scrape targets after the file becomes correct,
  without the need to restart vmagent.
  Previously scrape targets with invalid TLS CA file or TLS client certificate files
  were permanently dropped after the first attempt to initialize them, and they didn't
  appear until the next vmagent reload or the next change in other places of the loaded scrape configs.

- Make sure that TLS CA is properly re-loaded from file after it changes without the need to restart vmagent.
  Previously the old TLS CA was used until vmagent restart.

- Properly handle errors during http request creation for the second attempt to send data to remote system
  at vmagent and vmalert. Previously failed request creation could result in nil pointer dereferencing,
  since the returned request is nil on error.

- Add more context to the logged error during AWS sigv4 request signing before sending the data to -remoteWrite.url at vmagent.
  Previously it could miss details on the source of the request.

- Do not create a new HTTP client per second when generating OAuth2 token needed to put in Authorization header
  of every http request issued by vmagent during service discovery or target scraping.
  Re-use the HTTP client instead until the corresponding scrape config changes.

- Cache error at lib/promauth.Config.GetAuthHeader() in the same way as the auth header is cached,
  e.g. the error is cached for a second now. This should reduce load on CPU and OAuth2 server
  when auth header cannot be obtained because of temporary error.

- Share tls.Config.GetClientCertificate function among multiple scrape targets with the same tls_config.
  Cache the loaded certificate and the error for one second. This should significantly reduce CPU load
  when scraping big number of targets with the same tls_config.

- Allow loading TLS certificates from HTTP and HTTPs urls by specifying these urls at `tls_config->cert_file` and `tls_config->key_file`.

- Improve test coverage at lib/promauth

- Skip unreachable or invalid files specified at `scrape_config_files` during vmagent startup, since these files may become valid later.
  Previously vmagent was exitting in this case.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4959
2023-10-25 23:19:37 +02:00

199 lines
5.1 KiB
Go

package dns
import (
"context"
"flag"
"fmt"
"net"
"strconv"
"strings"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promscrape/discoveryutils"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutils"
)
// SDCheckInterval defines interval for targets refresh.
var SDCheckInterval = flag.Duration("promscrape.dnsSDCheckInterval", 30*time.Second, "Interval for checking for changes in dns. "+
"This works only if dns_sd_configs is configured in '-promscrape.config' file. "+
"See https://docs.victoriametrics.com/sd_configs.html#dns_sd_configs for details")
// SDConfig represents service discovery config for DNS.
//
// See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#dns_sd_config
type SDConfig struct {
Names []string `yaml:"names"`
Type string `yaml:"type,omitempty"`
Port *int `yaml:"port,omitempty"`
// RefreshInterval time.Duration `yaml:"refresh_interval"`
// refresh_interval is obtained from `-promscrape.dnsSDCheckInterval` command-line option.
}
// GetLabels returns DNS labels according to sdc.
func (sdc *SDConfig) GetLabels(_ string) ([]*promutils.Labels, error) {
if len(sdc.Names) == 0 {
return nil, fmt.Errorf("`names` cannot be empty in `dns_sd_config`")
}
ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
defer cancel()
typ := sdc.Type
if typ == "" {
typ = "SRV"
}
typ = strings.ToUpper(typ)
switch typ {
case "SRV":
ms := getSRVAddrLabels(ctx, sdc)
return ms, nil
case "MX":
ms := getMXAddrLabels(ctx, sdc)
return ms, nil
case "A", "AAAA":
return getAAddrLabels(ctx, sdc, typ)
default:
return nil, fmt.Errorf("unexpected `type` in `dns_sd_config`: %q; supported values: SRV, A, AAAA", typ)
}
}
// MustStop stops further usage for sdc.
func (sdc *SDConfig) MustStop() {
// nothing to do
}
func getMXAddrLabels(ctx context.Context, sdc *SDConfig) []*promutils.Labels {
port := 25
if sdc.Port != nil {
port = *sdc.Port
}
type result struct {
name string
mx []*net.MX
err error
}
ch := make(chan result, len(sdc.Names))
for _, name := range sdc.Names {
go func(name string) {
mx, err := resolver.LookupMX(ctx, name)
ch <- result{
name: name,
mx: mx,
err: err,
}
}(name)
}
var ms []*promutils.Labels
for range sdc.Names {
r := <-ch
if r.err != nil {
logger.Errorf("dns_sd_config: skipping MX lookup for %q because of error: %s", r.name, r.err)
continue
}
for _, mx := range r.mx {
target := mx.Host
for strings.HasSuffix(target, ".") {
target = target[:len(target)-1]
}
ms = appendMXLabels(ms, r.name, target, port)
}
}
return ms
}
func getSRVAddrLabels(ctx context.Context, sdc *SDConfig) []*promutils.Labels {
type result struct {
name string
as []*net.SRV
err error
}
ch := make(chan result, len(sdc.Names))
for _, name := range sdc.Names {
go func(name string) {
_, as, err := resolver.LookupSRV(ctx, "", "", name)
ch <- result{
name: name,
as: as,
err: err,
}
}(name)
}
var ms []*promutils.Labels
for range sdc.Names {
r := <-ch
if r.err != nil {
logger.Errorf("dns_sd_config: skipping SRV lookup for %q because of error: %s", r.name, r.err)
continue
}
for _, a := range r.as {
target := a.Target
for strings.HasSuffix(target, ".") {
target = target[:len(target)-1]
}
ms = appendAddrLabels(ms, r.name, target, int(a.Port))
}
}
return ms
}
func getAAddrLabels(ctx context.Context, sdc *SDConfig, lookupType string) ([]*promutils.Labels, error) {
if sdc.Port == nil {
return nil, fmt.Errorf("missing `port` in `dns_sd_config` for `type: %s`", lookupType)
}
port := *sdc.Port
type result struct {
name string
ips []net.IPAddr
err error
}
ch := make(chan result, len(sdc.Names))
for _, name := range sdc.Names {
go func(name string) {
ips, err := resolver.LookupIPAddr(ctx, name)
ch <- result{
name: name,
ips: ips,
err: err,
}
}(name)
}
var ms []*promutils.Labels
for range sdc.Names {
r := <-ch
if r.err != nil {
logger.Errorf("error in %s lookup for %q: %s", lookupType, r.name, r.err)
continue
}
for _, ip := range r.ips {
isIPv4 := ip.IP.To4() != nil
if lookupType == "AAAA" && isIPv4 || lookupType == "A" && !isIPv4 {
continue
}
ms = appendAddrLabels(ms, r.name, ip.IP.String(), port)
}
}
return ms, nil
}
func appendMXLabels(ms []*promutils.Labels, name, target string, port int) []*promutils.Labels {
addr := discoveryutils.JoinHostPort(target, port)
m := promutils.NewLabels(3)
m.Add("__address__", addr)
m.Add("__meta_dns_name", name)
m.Add("__meta_dns_mx_record_target", target)
return append(ms, m)
}
func appendAddrLabels(ms []*promutils.Labels, name, target string, port int) []*promutils.Labels {
addr := discoveryutils.JoinHostPort(target, port)
m := promutils.NewLabels(4)
m.Add("__address__", addr)
m.Add("__meta_dns_name", name)
m.Add("__meta_dns_srv_record_target", target)
m.Add("__meta_dns_srv_record_port", strconv.Itoa(port))
return append(ms, m)
}
var resolver = &net.Resolver{
PreferGo: true,
StrictErrors: true,
}